Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add SHAP interaction effects, fix minor bug, and add cox loss (#3043)

Browse Source 
* Add interaction effects and cox loss

* Minimize whitespace changes

* Cox loss now no longer needs a pre-sorted dataset.

* Address code review comments

* Remove mem check, rename to pred_interactions, include bias

* Make lint happy

* More lint fixes

* Fix cox loss indexing

* Fix main effects and tests

* Fix lint

* Use half interaction values on the off-diagonals

* Fix lint again
This commit is contained in:
Scott Lundberg
2018-02-07 18:38:01 -08:00
committed by Vadim Khotilovich
parent 077abb35cd
commit d878c36c84
19 changed files with 638 additions and 125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
src/predictor/cpu_predictor.cc
View File

@@ -215,7 +215,9 @@ class CPUPredictor : public Predictor {
void PredictContribution(DMatrix* p_fmat, std::vector<bst_float>* out_contribs,
const gbm::GBTreeModel& model, unsigned ntree_limit,
bool approximate) override {
bool approximate,
int condition,
unsigned condition_feature) override {
const int nthread = omp_get_max_threads();
InitThreadTemp(nthread, model.param.num_feature);
const MetaInfo& info = p_fmat->info();
@@ -232,12 +234,10 @@ class CPUPredictor : public Predictor {
// make sure contributions is zeroed, we could be reusing a previously
// allocated one
std::fill(contribs.begin(), contribs.end(), 0);
if (approximate) {
// initialize tree node mean values
#pragma omp parallel for schedule(static)
for (bst_omp_uint i = 0; i < ntree_limit; ++i) {
model.trees[i]->FillNodeMeanValues();
}
// initialize tree node mean values
#pragma omp parallel for schedule(static)
for (bst_omp_uint i = 0; i < ntree_limit; ++i) {
model.trees[i]->FillNodeMeanValues();
}
// start collecting the contributions
dmlc::DataIter<RowBatch>* iter = p_fmat->RowIterator();
@@ -263,7 +263,8 @@ class CPUPredictor : public Predictor {
continue;
}
if (!approximate) {
model.trees[j]->CalculateContributions(feats, root_id, p_contribs);
model.trees[j]->CalculateContributions(feats, root_id, p_contribs,
condition, condition_feature);
} else {
model.trees[j]->CalculateContributionsApprox(feats, root_id, p_contribs);
}
@@ -279,6 +280,50 @@ class CPUPredictor : public Predictor {
}
}
}
void PredictInteractionContributions(DMatrix* p_fmat, std::vector<bst_float>* out_contribs,
const gbm::GBTreeModel& model, unsigned ntree_limit,
bool approximate) override {
const MetaInfo& info = p_fmat->info();
const int ngroup = model.param.num_output_group;
size_t ncolumns = model.param.num_feature;
const unsigned row_chunk = ngroup * (ncolumns + 1) * (ncolumns + 1);
const unsigned mrow_chunk = (ncolumns + 1) * (ncolumns + 1);
const unsigned crow_chunk = ngroup * (ncolumns + 1);
// allocate space for (number of features^2) times the number of rows and tmp off/on contribs
std::vector<bst_float>& contribs = *out_contribs;
contribs.resize(info.num_row * ngroup * (ncolumns + 1) * (ncolumns + 1));
std::vector<bst_float> contribs_off(info.num_row * ngroup * (ncolumns + 1));
std::vector<bst_float> contribs_on(info.num_row * ngroup * (ncolumns + 1));
std::vector<bst_float> contribs_diag(info.num_row * ngroup * (ncolumns + 1));
// Compute the difference in effects when conditioning on each of the features on and off
// see: Axiomatic characterizations of probabilistic and
// cardinal-probabilistic interaction indices
PredictContribution(p_fmat, &contribs_diag, model, ntree_limit, approximate, 0, 0);
for (size_t i = 0; i < ncolumns + 1; ++i) {
PredictContribution(p_fmat, &contribs_off, model, ntree_limit, approximate, -1, i);
PredictContribution(p_fmat, &contribs_on, model, ntree_limit, approximate, 1, i);
for (size_t j = 0; j < info.num_row; ++j) {
for (int l = 0; l < ngroup; ++l) {
const unsigned o_offset = j * row_chunk + l * mrow_chunk + i * (ncolumns + 1);
const unsigned c_offset = j * crow_chunk + l * (ncolumns + 1);
contribs[o_offset + i] = 0;
for (size_t k = 0; k < ncolumns + 1; ++k) {
// fill in the diagonal with additive effects, and off-diagonal with the interactions
if (k == i) {
contribs[o_offset + i] += contribs_diag[c_offset + k];
} else {
contribs[o_offset + k] = (contribs_on[c_offset + k] - contribs_off[c_offset + k])/2.0;
contribs[o_offset + i] -= contribs[o_offset + k];
}
}
}
}
}
}
std::vector<RegTree::FVec> thread_temp;
};